design-game
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
npm run buildat the end of the process to verify that design changes did not break the project. This is a standard part of the developer workflow for the intended use-case. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the user's project files, creating a potential surface for indirect prompt injection if those files contain malicious instructions.
- Ingestion points: Reads
package.json,src/core/Constants.js, scene files, entity files, andsrc/core/EventBus.jsfrom the provided path. - Boundary markers: None. The agent is instructed to read these files directly without specific delimiters or warnings against embedded instructions.
- Capability inventory: The agent can modify files and execute shell commands (
npm run build). - Sanitization: None. The skill proceeds to analyze and implement changes based on the contents of the read files.
Audit Metadata